Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/dshakes/compass/onboardgit clone --depth 1 https://github.com/dshakes/compassWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00033 | $0.00891 |
| Opus 5 | $0.00016 | $0.00445 |
| Sonnet 5 | $0.00007 | $0.00178 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
onboard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboard me into this repo${ARGUMENTS:+ at $ARGUMENTS}.
Work through these steps in order. Use cheap subagents aggressively — Haiku for any mechanical run (installs, test execution, grepping), Sonnet for reasoning and writing. Ask before anything destructive; never push, merge, or deploy.
1 · Detect the stack
Scan the repo root for indicator files and print a one-line summary:
go.mod→ Go (note Go version)package.json→ Node; checkpnpm-lock.yaml/yarn.lock/package-lock.jsonfor the package managerCargo.toml→ Rust (note edition / MSRV from the manifest)pyproject.tomlorrequirements.txt→ Python; preferuvif availablemix.exs→ Elixir;Gemfile→ Ruby- Multiple files → polyglot; list all
2 · Install dependencies
Run the appropriate install command for each detected stack. Delegate this to a Haiku subagent — it's pure mechanics. Skip gracefully if deps are already present (cache hit / lockfile unchanged).
| Stack | Command |
|---|---|
| Go | go mod download |
| Node/npm | npm install |
| Node/pnpm | pnpm install |
| Node/yarn | yarn install |
| Rust | cargo fetch |
| Python (uv) | uv sync |
| Python (pip) | pip install -r requirements.txt or pip install -e . |
| Elixir | mix deps.get |
| Ruby | bundle install |
3 · Build + test
Find the correct commands — check Makefile targets, README, package.json scripts,
go.mod, Cargo.toml, pyproject.toml. Run them via a Haiku subagent.
Report PASS or FAIL with the last ~10 lines of output.
Do NOT fix failing tests now — just surface them.
Typical probes (in order):
make build && make test(if a Makefile with those targets exists)- Stack-native:
go build ./... && go test ./.../cargo test/npm test/pytest -q - Any
scripts.testentry inpackage.json
4 · Write or refresh CLAUDE.md
Invoke the bootstrap-agent-config skill — it inspects the repo and produces a
grounded CLAUDE.md (build command, test command, run command, key directories,
conventions). If the skill isn't available, do it yourself:
- Read existing
CLAUDE.md(if any); update only stale sections. - Ground every claim in code you actually read — no hallucinated commands.
- Keep it short: a dense page beats five vague ones.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 84 lines · 33 tokens per session scan A dd529a9919e4
onboard is a command published in the GitHub repository dshakes/compass (19 stars, last pushed 8d ago), licensed MIT. It adds 33 tokens to every session and 891 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.